Back to namelist

Yuri Lazebnik

scite, Inc
Co-Authors: Milo Mordaunt, Patrice Lopez, Peter Grabitz, Sean Rife, Josh Nicholson

scite: a deep learning platform to evaluate the veracity of scientific claims by citation analysis.

Studies from industry find that 50-90% of biomedical research cannot be independently verified. These reports highlight the fact that there is no available resource or indicator to determine how reliable a scientific claim is. The total citation count, the commonly used measure, is inherently a poor proxy for research quality because confirming and refuting citations are counted as equal. The lack of indicators for the veracity of reported claims costs the public, businesses, and governments, billions of dollars per year.
We have developed scite, a publicly available tool that extracts citation statements from scientific literature and automatically classifies them into those that provide supporting or contradicting evidence, or merely mention the claim. This unique resource enables scite users to evaluate the reliability of scientific claims at an unprecedented scale and speed, helping them to make better-informed decisions.

Download poster (.pdf)